skills.rest
nomad3
nomad3COMMUNITY
Explore all skills by this author →
GitHub

Entity Extraction

Extract named entities such as people, organizations, and locations from input text.

Updated Aug 23, 2026
Search Tags:#knowledge-graph#information-extraction#text-processing#entity-extraction#ner#named-entity-recognition
One-click install
npx skills add https://github.com/nomad3/servicetsunami-agents --skill entity-extraction
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Entity Extraction
Source: https://github.com/nomad3/servicetsunami-agents/tree/main/apps/api/app/skills/entity_extraction
Command: npx skills add https://github.com/nomad3/servicetsunami-agents --skill entity-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Named entity extraction from unstructured text enables faster data enrichment, knowledge-graph population, and smarter search by turning raw text into structured entities.

Core Features & Use Cases

  • Named-entity recognition: Identify and classify entities such as people, organizations, locations, and concepts from text.
  • Knowledge graph enrichment: Link extracted entities to a knowledge graph for later retrieval and insights.
  • Use case: Process customer conversations or documents to populate an entity index for CRM search and analytics.

Quick Start

Provide a short text sample and ask the skill to extract named entities.

Frequently Asked Questions about Entity Extraction

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract named entities from unstructured text for a knowledge graph?▼

Named entity recognition extracts people, organizations, locations, and concepts from unstructured text to populate a knowledge graph. You provide a text sample and the skill classifies and outputs structured entities for retrieval and insights.

Can I use this for text processing pipelines to enrich customer conversation data?▼

Yes, text processing pipelines use entity extraction to enrich customer conversation data. Processing documents or conversations populates an entity index for CRM search and analytics, turning raw text into structured, searchable data.

What types of entities can named entity recognition identify from my documents?▼

Named entity recognition identifies people, organizations, locations, and concepts from your documents. The skill applies configurable models to classify these entities during the text processing workflow.

Do I need to configure models before extracting entities from input text?▼

The skill supports configurable models and post-processing options for entity extraction. You provide a short text sample to start, and the named entity recognition logic handles the extraction and classification.

What is the best way to turn raw text into structured entities for data enrichment?▼

The best way to turn raw text into structured entities for data enrichment is using named entity recognition. This skill classifies people, organizations, locations, and concepts, enabling faster data enrichment and smarter search.

Are there limitations when applying named entity recognition to complex documents?▼

Named entity recognition accuracy depends on the configurable models used and the complexity of the input text. Post-processing options help refine results, but highly ambiguous or unstructured text may require additional validation.

Related Skills

Explore More Data & Analytics Skills→
kishorkukrejakishorkukreja
56

nlp-supply-chain

Apply NLP techniques to supply chain text for extraction and classification.

Community
Advanced
OriNachumOriNachum
234

neo4j-query

Query Neo4j knowledge graphs to retrieve entities and relationships.

Community
Intermediate
semantica-agisemantica-agi
3.0k

ingest

Ingest data from files, databases, APIs, or streams into Semantica knowledge graphs.

Official
Intermediate
dkyazzentwatwadkyazzentwatwa
86

named-entity-extractor

Extract people, organizations, and locations from unstructured text using NLP.

Community
Intermediate